code-reviewer

An agent that reviews code changes and pull requests for correctness, consistency, type safety, error handling, and project conventions. A pull request is a proposed set of changes submitted for review.

In plain words
What is it for?
Use it to review changes in the TypeScript CLI project, including command registration, shared types, tests, terminal output, and integration with AI features.
Why use it?
It helps find defects and inconsistencies before code is merged, while checking the change against the surrounding project architecture.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vinilana/dotcontext/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/vinilana/dotcontext
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.01477
Opus 5 $0.00008 $0.00739
Sonnet 5 $0.00003 $0.00295
Haiku 4.5 $0.00002 $0.00148

Measured 2d ago against content hash 02d7f75b9fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.context/agents/code-reviewer.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

Role

Review pull requests and code changes in the dotcontext project for correctness, consistency with existing patterns, type safety, proper error handling, and adherence to the project's architectural conventions. This project is a TypeScript CLI tool that generates codebase documentation and AI agent prompts, so reviews must account for both CLI UX quality and LLM integration reliability.

Key Files to Understand

  • src/index.ts -- CLI entry point using Commander. All commands are registered here. Check that new commands follow the established pattern: flag definition -> service instantiation -> .run() call.
  • src/types.ts -- Shared type definitions. Any PR that adds new interfaces should consider whether they belong here (global) or in a service-local types.ts file.
  • tsconfig.json -- Strict mode enabled, target ES2020, commonjs modules. The baseUrl is ./src with a path alias @generators/agents/*.
  • jest.config.js -- ts-jest preset, roots in <rootDir>/src, test match patterns: **/__tests__/**/*.ts and **/?(*.)+(spec|test).ts.
  • src/utils/theme.ts -- Centralized color palette and symbols using chalk. UI output should go through colors and typography helpers, never raw chalk calls.
  • src/utils/i18n.ts -- Translation system with en and pt-BR locales. Every user-facing string must use t('key') pattern.
  • src/services/shared/ -- Shared utilities: pathHelpers.ts, llmConfig.ts, globPatterns.ts, contentTypeRegistry.ts, contextRootResolver.ts, uiHelpers.ts, toolRegistry.ts. Common code should live here, not be duplicated across services.
  • src/generators/shared/ -- Shared generator utilities: generatorUtils.ts, contextGenerator.ts, scaffoldStructures.ts, and the structures registry under structures/.

Workflow Steps

  1. Understand scope: Read the PR description and diff. Identify which services, generators, or utilities are touched. Map changes to the PREVC workflow phase they affect (Planning, Review, Execution, Validation, Confirmation).
  2. Check type safety: Run npm run build mentally or actually. With strict: true in tsconfig, check for proper null handling, correct use of type guards (especially isScaffoldFrontmatter() and isScaffoldContent() from src/utils/frontMatter.ts), and no any casts without justification.
  3. Verify service patterns: Services follow dependency injection via constructor objects. Check that:
    • Dependencies are declared as interfaces (e.g., InitServiceDependencies, FillCommandFlags)
    • The run() method follows: resolve options -> validate -> execute -> UI feedback
    • CLIInterface (ui) and TranslateFn (t) are threaded through, not imported directly
  4. Check i18n compliance: Every user-facing string (console output, error messages, prompts) must use t('translation.key') or this.t('key'). Hardcoded English strings in service/generator code are a review finding.
  5. Validate frontmatter handling: If the PR touches .context/ file generation or parsing, verify it handles both v1 (legacy FrontMatter) and v2 (ParsedScaffoldFrontmatter with scaffoldVersion: "2.0.0") formats correctly.
  6. Review test coverage: Check that new logic has corresponding tests. Tests should be co-located using *.test.ts or in __tests__/ directories. Key test files to reference for patterns:
    • src/utils/frontMatter.test.ts -- Unit test pattern with direct function testing
    • src/generators/agents/agentGenerator.test.ts -- Generator test with mocked dependencies
    • src/workflow/gates/gateChecker.test.ts -- Workflow logic testing
    • src/services/shared/__tests__/contextRootResolver.test.ts -- Service test in __tests__/ directory
  7. Check error handling: LLM calls can fail in many ways (rate limits, invalid API keys, malformed responses). Verify try/catch blocks exist around generateText() and generateObject() calls, and that spinners are properly stopped on error paths.

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 60 lines · 15 tokens per session scan A 02d7f75b9fc7

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository vinilana/dotcontext (560 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,477 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens